Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,14 @@
+base_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
+gate_mode: hidden 
+dtype: bfloat16 
+experts_per_token: 2
+experts:
+  - source_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
+    positive_prompts:
+      - "think step by step"
+    ## (optional)
+    # negative_prompts:
+    #   - "This is a prompt expert_model_1 should not be used for"
+  - source_model: /home/Ubuntu/Desktop/mergekit/models/NeuralOmniWestBeaglake-7B
+    positive_prompts:
+      - "storytelling"

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183de835674b930a471495f96357df628321a98e47ad0893d1907c4afcc3ba79
+size 1983949904

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45a2eb9f363e49458b034304aba5c065fe1cfa4b2ff9435a5750ed7f72b46cc
+size 1895878496

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b25449b3f230a41d12af8fd9395494bee3e57d39d5f8e89e3fe78adccbc801
+size 1929415992

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01cb46cd51c5654921cea153ffd9b5c44b450ddc498c2725323efa1de33648e
+size 1895878504

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d5d48691147de561623d0bdacd998744b01a28515d84473fb2e866c4640a62
+size 1929416000

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724e542bde53e91389558514a8171f27aca315aa74b591617d2e64cebc3abd56
+size 1979756320

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca297a639190873d3533b07060a0afa919ec5c30f2c70fa23318fa3909a528e
+size 1962978872

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae606a07bd17b2790a7dfefb71a8405850cc1f56cbbca8ad77e91f3d1797302
+size 1979756320

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e4114172968f6bfa4ae4d0d212d494ee47fcf4adb967d8287df8128cdfc552
+size 1962978872

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa15dcc2df1bc22793d8db5bd2fc2b894d631e1f5bc90a6f437acfaf7cabe5d
+size 1979756320

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6f959b568af54cf23db2fb8852b84e3b8374e27a653ffa9f3c5ed2512eea9c
+size 1962978872

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d331e8cadb01d62f71116024f2268ba0a78ecd8e5defe24e1cf3c0e4f4d9b94
+size 1979756320

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1021963fedb0bf97854f3fdbb91be984df55b3e77ddcd05a4e7d647579b73dd
+size 1962978872

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92eeb97e78c406df3598836a0e644c910d33d9e697a8d3eedcfdbd763aa1180
+size 352849856

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.norm.weight": "model-00001-of-00014.safetensors", "lm_head.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00014.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00014.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00014.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00014.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00014.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00014.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00014.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00014.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00014.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00014.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00014.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00014.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00014.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00014.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}